scholarly journals On the Cryptanalysis of Two Cryptographic Algorithms That Utilize Chaotic Neural Networks

2015 ◽  
Vol 2015 ◽  
pp. 1-9 ◽  
Author(s):  
Ke Qin ◽  
B. John Oommen
Keyword(s):  
Neural Networks ◽  
Hash Function ◽  
Chaotic Map ◽  
Coupled Map Lattice ◽  
Encryption Algorithm ◽  
Chaotic Neural Networks ◽  
Relative Ease ◽  
Cryptographic Algorithms ◽  
The One

This paper deals with the security and efficiency issues of two cipher algorithms which utilize the principles of Chaotic Neural Networks (CNNs). The two algorithms that we consider are (1) the CNN-Hash, which is a one-way hash function based on the Piece-Wise Linear Chaotic Map (PWLCM) and the One-Way Coupled Map Lattice (OCML), and (2) the Delayed CNN-Based Encryption (DCBE), which is an encryption algorithm based on the delayed CNN. Although both of these cipher algorithms have their own salient characteristics, our analysis shows that, unfortunately, the CNN-Hash is not secure because it is neither Second-Preimage resistant nor collision resistant. Indeed, one can find a collision with relative ease, demonstrating that its potential as a hash function is flawed. Similarly, we show that the DCBE is also not secure since it is not capable of resisting known plaintext, chosen plaintext, and chosen ciphertext attacks. Furthermore, unfortunately, both schemes are not efficient either, because of the large number of iteration steps involved in their respective implementations.

An Improved Block Cryptosystem Based on Iterating Delayed Chaotic Neural Networks

2013 ◽  
Vol 380-384 ◽  
pp. 2623-2628
Author(s):  
Xin Guo Zou
Keyword(s):  
Neural Networks ◽  
Block Cipher ◽  
Chaotic Map ◽  
Binary Sequences ◽  
Time Varying ◽  
Chosen Plaintext Attack ◽  
Chaotic Neural Networks ◽  
Time Varying Delay ◽  
Delayed Chaotic Neural Networks ◽  
Varying Delay

Recently, a large number of chaotic cryptosystems have been proposed, many of them fundamentally flawed by lack of robustness and security. In this paper, we point out the weakness of a very recent block cipher algorithm which is based on the chaotic Hopfield neural networks with time varying delay and give the improved scheme of it. We provide the chosen plaintext attack to recover the permuted plaintext string, and point out that the encryption speed is not fast enough. It is shown that the dependence on the key, but not on the plaintext, to generate binary sequences of iterating the chaotic map mechanism facilitates leakage of the information and vulnerable been attacked. Based on such a fact, we give the improved scheme to obtain higher security and faster speed.

Image Encryption Algorithm Based on Substitution Principle and Shuffling Scheme

2020 ◽  
Vol 38 (3B) ◽  
pp. 98-103
Author(s):  
Atyaf S. Hamad ◽  
Alaa K. Farhan
Keyword(s):  
Image Encryption ◽  
Chaotic Map ◽  
Logistic Map ◽  
Encryption Algorithm ◽  
Second Phase ◽  
Cipher Text ◽  
The Face ◽  
Substitution Principle ◽  
2D Logistic Map ◽  
Image Encryption Algorithm

This research presents a method of image encryption that has been designed based on the algorithm of complete shuffling, transformation of substitution box, and predicated image crypto-system. This proposed algorithm presents extra confusion in the first phase because of including an S-box based on using substitution by AES algorithm in encryption and its inverse in Decryption. In the second phase, shifting and rotation were used based on secrete key in each channel depending on the result from the chaotic map, 2D logistic map and the output was processed and used for the encryption algorithm. It is known from earlier studies that simple encryption of images based on the scheme of shuffling is insecure in the face of chosen cipher text attacks. Later, an extended algorithm has been projected. This algorithm performs well against chosen cipher text attacks. In addition, the proposed approach was analyzed for NPCR, UACI (Unified Average Changing Intensity), and Entropy analysis for determining its strength.

scholarly journals Deep Neural Networks Classification via Binary Error-Detecting Output Codes

2021 ◽  
Vol 11 (8) ◽  
pp. 3563
Author(s):  
Martin Klimo ◽  
Peter Lukáč ◽  
Peter Tarábek
Keyword(s):  
Neural Networks ◽  
Categorical Data ◽  
Coding Theory ◽  
Hamming Distance ◽  
Activation Function ◽  
Block Codes ◽  
Ease Of Use ◽  
Linear Block Codes ◽  
Binary Coding ◽  
The One

One-hot encoding is the prevalent method used in neural networks to represent multi-class categorical data. Its success stems from its ease of use and interpretability as a probability distribution when accompanied by a softmax activation function. However, one-hot encoding leads to very high dimensional vector representations when the categorical data’s cardinality is high. The Hamming distance in one-hot encoding is equal to two from the coding theory perspective, which does not allow detection or error-correcting capabilities. Binary coding provides more possibilities for encoding categorical data into the output codes, which mitigates the limitations of the one-hot encoding mentioned above. We propose a novel method based on Zadeh fuzzy logic to train binary output codes holistically. We study linear block codes for their possibility of separating class information from the checksum part of the codeword, showing their ability not only to detect recognition errors by calculating non-zero syndrome, but also to evaluate the truth-value of the decision. Experimental results show that the proposed approach achieves similar results as one-hot encoding with a softmax function in terms of accuracy, reliability, and out-of-distribution performance. It suggests a good foundation for future applications, mainly classification tasks with a high number of classes.

Sign in / Sign up

Export Citation Format

Share Document